A three-stage deep learning system which can figure out how to imitate a person's voice from as little as five seconds of recorded speech. Speaks with the deepfaked voice in realtime. The sample is used to condition an existing TTS model to sound like someone.
Running it inside a Docker container: https://sean.lane.sh/posts/2019/07/Running-the-Real-Time-Voice-Cloning-project-in-Docker/
The eSpeak NG (Next Generation) Text-to-Speech program is an open source speech synthesizer that supports 102 languages and accents, based on the eSpeak engine created by Jonathan Duddington. It supports spectral and Klatt formant synthesis, and the ability to use MBROLA voices.
An archive of recorded messages and error tones from United States telephony networks. Available for online listening or free download.
github repo for a foss speechrecognition system that has multiple models for speech interpretation.
A way to donate your voice to build speech synthesizers for people. In a way, you can back up your voice if you think you're going to lose it.
A Python module which implements interfaces to the native text-to-speech API for whatever platform you're running it on, be it Windows, MacOSX, or Espeak on Linux.